Closed
Conversation
This way, we're able to have the fallback skill ask for the user to repeat themself one time, and then stop asking.
This was referenced Feb 27, 2025
Owner
|
Thank you!
Yeah the skills were never meant to know anything about the state of the conversation, so unfortunately this means the code architecture does not help achieving this. I gave it a try at modifying the architecture two times, too, and ended up with #296 which I prefer a bit over this PR (though I still don't like it so much that a skill gets access to possibly the SkillOutput of another skill). So I'm closing in favor of #296 but thanks for the input! Let me know what you think about #296 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR makes the fallback skill re-enable the microphone one time when the user says something that it can't understand. Of course, it's possible that the speech that Dicio is hearing is not directed at it, so it doesn't make sense to retry indefinitely: if the user's second attempt is also something that Dicio can't understand, this implementation omits the "Could you repeat?" part of the response and stops re-enabling the microphone until the user successfully performs another interaction.
Fixes #280.
I'm not totally happy about the fact that this PR requires me to move InteractionLog into the skill/ module, but I didn't see another good solution.